Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.7233. Min Act: -0.1700
Data Index: 5640070 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.7233. Min Act: -0.1700
Data Index: 1427650 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.7233. Min Act: -0.1700
Data Index: 7801929 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.6607. Min Act: -0.1700
Data Index: 2506334 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.6294. Min Act: -0.1700
Data Index: 2297418 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.6294. Min Act: -0.1700
Data Index: 4665583 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5981. Min Act: -0.1700
Data Index: 6653535 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5981. Min Act: -0.1700
Data Index: 3958407 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5825. Min Act: -0.1700
Data Index: 5297787 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5825. Min Act: -0.1700
Data Index: 7268248 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5668. Min Act: -0.1700
Data Index: 8023810 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5512. Min Act: -0.1700
Data Index: 3505002 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5668. Min Act: -0.1700
Data Index: 336181 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5825. Min Act: -0.1700
Data Index: 2234350 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5512. Min Act: -0.1700
Data Index: 2027260 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5512. Min Act: -0.1700
Data Index: 3260350 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5512. Min Act: -0.1700
Data Index: 5425071 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5355. Min Act: -0.1700
Data Index: 5616628 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5512. Min Act: -0.1700
Data Index: 7551793 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5512. Min Act: -0.1700
Data Index: 7540397 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19